Mèo của chúng tôi đang chạy đi lấy dữ liệu cho bạn ...

Hỗ Trợ Đồ Án – Sàn thương mại bán code kiếm tiền số 1 Việt Nam

Hỗ Trợ Đồ Án

ANDROID MALWARE CLASSIFICATION USING DEEP LEARNING

Gửi thông báo lỗi Báo cáo vi phạm bản quyền

[PE202559] ANDROID MALWARE CLASSIFICATION USING DEEP LEARNING -33%

Upload bởi:

kimcuongt3

(0 Đánh giá)

180,000đ

120,000đ

In the present day, there is a growing inclination towards the adoption of digitaltransformation and artificial intelligence in smart device applications across diverse operating systems. This trend aligns with the advancements of the fourth industrial revolution and is being observed in numerous domains of social and economic activity.

Danh mục Mã độc

Loại Tài liệu

Ngày tải lên 14/03/2025

File download hotrodoan.vn_mã độc.pdf

Lưu bài

Chức năng đầy đủ và giống demo 100%
Hỗ trợ lắp đặt nếu cần
Hỗ trợ trả lời người mua sau khi tải

Nguyễn Kim Cường

Xem trang

Bài đăng
129

Đánh giá (0)
0/5

Ngày tham gia
11/03/2025

Research on the efficiency improvement of Android malware detection and classification is significant. Solving this problem thoroughly requires research, as Android malware significantly impacts mobile users. The work has been done in the dissertation:

Survey on research related to detecting and classifying malware on Android from the inception of the Android operating system until now (especially studies from 2019 to the present). From these studies, I now have a more general view of the research directions in the problem of detecting and classifying malware on Android. Regarding feature augmentation, I applied algorithms to augmentation features (Comatrix and Apriori), creating connections between features.

Regarding feature selection, I proposed a new method for the feature selection problem (based on popularity and contrast calculation).

Regarding machine learning models and deep learning models, in the dissertation, I have applied traditional machine learning models such as SVM, KNN, and RF. Deep learning models such as DBN, CNN, RNN, etc. These models give positive experimental results. In addition to applying these existing models, I used the WDCNN model, which is improved from the CNN model. Experimentally, this model has many advantages and gives higher results than other deep learning models.

ĐIỂM TRUNG BÌNH